CN109613362B - Non-invasive electric appliance quantity identification method - Google Patents
Non-invasive electric appliance quantity identification method Download PDFInfo
- Publication number
- CN109613362B CN109613362B CN201811536276.6A CN201811536276A CN109613362B CN 109613362 B CN109613362 B CN 109613362B CN 201811536276 A CN201811536276 A CN 201811536276A CN 109613362 B CN109613362 B CN 109613362B
- Authority
- CN
- China
- Prior art keywords
- real
- value
- time
- effective
- electric appliance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/02—Measuring effective values, i.e. root-mean-square values
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/25—Arrangements for measuring currents or voltages or for indicating presence or sign thereof using digital measurement techniques
- G01R19/2506—Arrangements for conditioning or analysing measured signals, e.g. for indicating peak values ; Details concerning sampling, digitizing or waveform capturing
Abstract
The invention relates to the field of electric appliance identification, and provides a non-invasive electric appliance quantity identification method aiming at the problem that early non-invasive monitoring depends on hardware and an algorithm, which comprises the following steps: s1, when the N electric appliances operate independently, the individual real-time currents of the N electric appliances in the preset collection quantity with the same phase as a starting point are obtained respectively; s2, acquiring total real-time current with a preset acquisition quantity after the same phase is taken as a starting point in actual operation; s3, setting the value range of the number of each electric appliance in the previous step, and generating an initial solution corresponding to the predicted operation number of each electric appliance in the previous step; s4, judging whether the initial solution meets a preset effective condition, if so, storing the initial solution as an effective solution into an effective solution set; if no initial solution satisfies the predetermined condition, S2 is entered; and S4, calculating the matching degree of the expected total real-time current corresponding to the effective solution and the total real-time current in the S2, wherein the effective solution with the highest matching degree is the optimal solution. The invention is suitable for non-invasive identification of the electric appliance.
Description
Technical Field
The invention relates to the field of electric appliance identification, in particular to a non-invasive electric appliance quantity identification method.
Background
In the 70 s of the 20 th century, the U.S. and some European countries began to research the household energy consumption in order to improve the household electricity utilization efficiency and realize energy conservation and emission reduction. In recent years, with the development of sensing technology, information communication technology and control technology, especially the rise of smart grids, the tasks of home energy management systems are also increasing, and the premise for realizing the tasks is to effectively monitor various electric appliances. The power load monitoring has great significance for families, power companies and the like, and for families, the power utilization condition of each type of electric appliance can be clearly known, and the power utilization habit is adjusted according to the power utilization condition to achieve the purpose of energy conservation; for the electric power company: the power utilization of each region can be known, different packages are made according to the power utilization, reasonable power allocation is achieved, and the maximum utilization of resources is achieved.
Currently, the monitoring of the power load can be divided into two types:
1) traditional invasive detection realizes the measurement through increasing corresponding sensor branch way for all kinds of electrical apparatus, and then the consumption monitoring of the total electrical apparatus that realizes, and its input is great, causes the interference to the normal operation of electrical apparatus easily, and too much circuit access makes user's acceptance not very good yet.
2) The non-intrusive detection power consumption proposed in the early stage can only decompose the category based on the unit current of the category of the electric appliance, and cannot be detailed to a specific electric appliance. And most of non-intrusive electric appliance quantity identification methods in power consumption detection rely on transient characteristic data of electric appliances, the requirements on hardware are high, the cost is correspondingly improved, the popularization of products is not facilitated, algorithms are too complex and inconvenient to integrate into hardware equipment, and a large amount of labor cost is required in the early stage when training data are too much.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the problem that the existing non-invasive electric appliance quantity identification method depends on complicated hardware and algorithm, the non-invasive electric appliance quantity identification method is provided.
The invention solves the technical problems and adopts the technical scheme that:
the non-invasive electric appliance quantity identification method comprises the following steps:
s1, when N electric appliances run independently, obtaining the individual real-time current of the preset sampling number of each electric appliance with the same phase as a starting point, wherein the preset sampling number is more than or equal to the current period divided by the sampling period, N is more than or equal to 2, and the individual real-time current of the kth sampling of the kth electric appliance relative to the starting point is recorded as ikt，k∈[1,N]Let the predetermined number of samples be B, t ∈ [1, B ]]；
S2, when N electric appliances are actually operated and the number of the operated electric appliances is unknown, acquiring total real-time current of the N electric appliances with the preset sampling number by taking the same phase as a starting point, and recording the total real-time current of the t-th sampling as it，t∈[1,B]；
S3, setting the value range of the operation quantity of each electric appliance in actual operation in the step S2, and generating an initial solution according to the value range to form an initial solution set, wherein the initial solution corresponds to the predicted operation quantity of each electric appliance in the step S2;
s4, according to the individual real-time current and the overall real-time current, judging whether the initial solution in the initial solution set meets a preset effective condition or not, if so, storing the corresponding initial solution as an effective solution in an effective solution set; if none of the initial solutions satisfies the predetermined validity condition, go to step S2;
s5, calculating the corresponding expected total real-time current according to the individual real-time current and the effective solutions, calculating the matching degree of the expected total real-time current corresponding to each effective solution and the total real-time current in the step S2, and selecting the effective solution with the highest matching degree as the optimal solution of the initial solution set in the step S2.
Preferably, the step S1 includes:
s101, selecting N electric appliances as research objects, respectively collecting real-time current and real-time voltage of each electric appliance A times, and recording the t' th sampled real-time voltage of the kth electric appliance as vkt′Recording the real-time current of the t 'sampling of the kth electrical appliance as i'kt′，k∈[1,N]，t′∈[1,A]A is more than or equal to B; taking the average value of the maximum value and the minimum value of the real-time voltage of the kth electric appliance as the voltage v corresponding to the initial 0 phase of the kth electric appliancepSetting the sampling frequency p corresponding to the initial 0-phase real-time voltage as 0 and setting the initial value of the current traversed sampling frequency c as 1;
s102, judging whether A is larger than or equal to c, if so, entering the step S103; otherwise, go to step S104;
s103, judging whether c is more than or equal to p and | vp-vkc| is less than or equal to a predetermined threshold value, vkcIf so, entering step S104, otherwise, increasing c by 1, and entering step S102;
s104, judging whether the real-time voltage after the current traversal sampling times is complete, if so, entering a step S106, otherwise, entering a step S105;
s105, increasing a preset amplitude value by a preset threshold value, setting p to be 0, and entering a step S102;
s106, judgment vkcWhether the real-time voltages of the next preset number meet the ascending trend or not is judged, if yes, p is set to be equal to c, and B real-time currents i 'are intercepted by taking the sampling times p as a starting point'kp～i′k(B+p-1)As individual real-time current of the corresponding appliance, i.e. setting ik1＝i′kp，ikB＝i′k(B+p-1)And the individual real-time current i of the kth type of electric appliance is obtained by analogyk1～ikB(ii) a Otherwise, the step S107 is carried out;
s107, increasing the predetermined threshold value by a predetermined amplitude value, setting p equal to c, increasing c by 1, and entering step S102.
Preferably, the step S2 includes:
s201, when N electrical appliances are actually operated and the actual quantity of each electrical appliance is unknown, acquiring real-time current and real-time voltage in A actual operation, and recording the t' th sampled real-time voltage as vt′And recording the real-time current of the t 'th sampling as i't，t′∈[1,A]A is more than or equal to B; the average value of the maximum value and the minimum value of the real-time voltage is used as the voltage v 'corresponding to the initial 0 phase'pSetting the sampling frequency p corresponding to the initial 0-phase real-time voltage value as 0, and setting the initial value of the current traversed sampling frequency c as 1;
s202, judging whether A is larger than or equal to c, if so, entering the step S203; otherwise, go to step S204;
s203, judging whether c is more than or equal to p and | v'p-vc| is less than or equal to a predetermined threshold value, vcIf the real-time voltage sampled for the c-th time is the real-time voltage sampled for the c-th time, the step S204 is performed, otherwise, the step C is increased by 1, and the step S202 is performed;
s204, judging whether the real-time voltage after the current traversal sampling times is complete, if so, entering a step S206, otherwise, entering a step S205;
s205, increasing a predetermined amplitude value by a predetermined threshold value, setting p to be 0, and entering step S202;
s206, judgment vcWhether the latter predetermined number of real-time voltages areMeeting the ascending trend, if so, setting p to be equal to c, and intercepting B real-time currents i 'by taking the sampling times p as a starting point'p～i′B+p-1As a total real-time current, i.e. setting i1＝i′p，iB＝i′B+p-1And so on to obtain the real-time current i1～iB(ii) a Otherwise, go to step S207;
s207, increasing the predetermined threshold value by a predetermined amplitude value, setting p equal to c, increasing c by 1, and entering step S202.
Preferably, the step S3 includes:
s301, setting the value range of the running quantity of each electric appliance in the step S2;
and S302, randomly generating Q initial solutions according to the value range to form an initial solution set.
Preferably, step S3 is followed by:
calculating the maximum value and the minimum value of the individual real-time current of each electrical appliance, calculating the difference value of the maximum value and the minimum value of the individual real-time current of each electrical appliance as an individual amplitude difference value, and recording the maximum value, the minimum value and the individual amplitude difference value of the individual real-time current of the kth electrical appliance as
And Dk；
Calculating the total real-time current i1～iBThe effective value, the maximum value and the minimum value of (A) are sequentially recorded as
iUAnd iLAnd calculating the difference value between the maximum value and the minimum value of the total real-time current as a total amplitude difference value D.
Preferably, the predetermined effective conditions include:
recording the maximum value and the minimum value of the maximum values and the minimum values of the individual real-time currents corresponding to all the non-zero operation quantities in the initial solution as iU1And iL1Maximum value of total real-time current iUI is greater than or equal to a predetermined multipleU1And maximum of total real-time currentSmall value of iLIs less than or equal to iL1The preset multiple is at least the operation quantity of the electric appliance corresponding to the maximum value of the real-time current of each electric appliance during the individual operation in the initial solution;
and/or, subtracting the total amplitude difference value from the sum of the products of the running quantity of each electric appliance and the individual amplitude difference value of the corresponding electric appliance in the effective solution, wherein the total amplitude difference value is less than or equal to a preset difference value;
and/or recording the maximum value and the minimum value of the effective values of the individual real-time currents of the kth electric appliance obtained for multiple times as
And
the effective value of the total real-time current is more than or equal to the sum of products of the quantity of each electric appliance in the effective solution and the minimum value of the effective value of the corresponding individual real-time current and less than or equal to the sum of products of the quantity of each electric appliance in the effective solution and the maximum value of the effective value of the corresponding individual real-time current.
Preferably, the step S5 includes:
s501, recording the effective value of the individual real-time current of the kth electric appliance as
Noting that the number of valid solutions is R, the corresponding y-th valid solution is { F'1y～F′Ny}，y∈[1,R]，F′kyCalculating the current ratio of each electric appliance corresponding to the effective solution for the operation number of the kth electric appliance in the yth effective solution, and recording the current ratio corresponding to the yth effective solution as Gky，
S502, multiplying the current ratio of each electric appliance by the corresponding individual real-time current to obtain weighted individual real-time current, effectively solving the corresponding expected total real-time current to be the sum of the weighted individual real-time currents of all the electric appliances at the corresponding acquisition points, and recording the t-th time under the y-th effective solutionThe expected total real-time current of the sample is i'ty，
S503, calculating the variance between the expected real-time current and the total real-time current in the step S2, and recording the variance corresponding to the y-th effective solution as Xy，
The variance corresponding to all valid solutions is noted as X1～XR；
S504, taking the variance as the matching degree of the corresponding effective solution, and selecting X1～XRThe effective solution corresponding to the maximum value in the initial solution set is used as the optimal solution of the initial solution set.
Preferably, the step S5 includes:
the step S5 includes:
s501, recording the effective value of the individual real-time current of the kth electric appliance as
Noting that the number of valid solutions is R, the corresponding y-th valid solution is { F'1y～F′Ny}，y∈[1,R]，F′kyCalculating the current ratio of each electric appliance corresponding to the effective solution for the operation number of the kth electric appliance in the yth effective solution, and recording the current ratio corresponding to the yth effective solution as Gky，
S502, multiplying the current ratio of each electric appliance by the corresponding individual real-time current to obtain the weighted individual real-time current, wherein the expected overall real-time current corresponding to the effective solution is the sum of the weighted individual real-time currents of all the electric appliances at the corresponding acquisition points, and the expected overall real-time current sampled at the t time under the y-th effective solution is recorded as i'ty，
S503, calculating the variance between the expected real-time current and the total real-time current in the step S2, and recording the variance corresponding to the y-th effective solution as Xy，
The variance corresponding to all valid solutions is noted as X1～XRTo X1～XREndowing corresponding 1 st preset weight to R th preset weight according to the sorting size to obtain new variance corresponding to all effective solutions, and recording the variance as X'1～X′R；
S504, calculating the sum of the running quantity of each electric appliance in the effective solution multiplied by the individual amplitude difference value of each electric appliance and subtracting the total amplitude difference value to obtain an amplitude difference value, and recording the amplitude difference value corresponding to the yth effective solution as Zy1，
The difference of the amplitude difference corresponding to all the effective solutions is recorded as Z11～ZR1(ii) a To Z11～ZR1Giving corresponding 1 ' preset weight to R ' preset weight according to the sorting size to obtain new amplitude difference values corresponding to all effective solutions, and recording the new amplitude difference values as Z '11～Z′R1；
S505, calculating the sum of the running quantity of each electric appliance in the effective solution multiplied by the effective value of the real-time current corresponding to each electric appliance individual and subtracting the effective value of the real-time current to obtain an effective value difference value, and recording the effective value difference value corresponding to the yth effective solution as Zy2，
The difference of the effective values corresponding to all effective solutions is recorded as Z12～ZR2(ii) a To Z12～ZR2Giving corresponding 1 st ' preset weight to the R th ' preset weight according to the sorting size to obtain new effective value difference values corresponding to all effective solutions, and recording the difference values as Z '12～Z′R2；
S506, corresponding to the variance X of the effective solution1′～XR', amplitude difference valueZ′11～Z′R1And an effective difference value Z'12～Z′R2And adding the effective solutions to obtain the matching degree of the corresponding effective solutions, and selecting the effective solution with the highest matching degree as the optimal solution of the initial solution set.
Further, the step S1 is executed for multiple times to obtain multiple groups of individual real-time currents, and the effective value of the individual real-time current of the kth electrical appliance is an average value of the effective values of the individual real-time currents of the kth electrical appliance in the multiple groups of individual real-time currents.
Preferably, the 1 st to Rth predetermined weights may be sequentially set to W1、2W1……RW1The step of giving the corresponding 1 st to R-th predetermined weights according to the sorting size to obtain new variances corresponding to all valid solutions includes: the least ranked variance is given a weight of W1The largest ranked variance is given weight RW1And so on;
and/or, the 1 'th to R' th predetermined weights may be sequentially set to W2、2W2……RW2The step of giving the corresponding 1 st 'to R' predetermined weights according to the sorting size to obtain new amplitude difference values corresponding to all valid solutions includes: the smallest ordered amplitude difference value is given a weight of W2The greatest ranked difference value is weighted by RW2And so on;
and/or, the 1 st 'to R' predetermined weights may be sequentially set to W3、2W3……RW3The step of giving the corresponding 1 st 'to R' preset weights according to the sorting size to obtain the new effective value difference values corresponding to all the effective solutions comprises the following steps: the smallest sorted effective value difference is given weight W3The most significant difference value in the sequence is weighted by RW3And so on.
The invention has the beneficial effects that:
compared with the prior art, the method only depends on the steady-state current and voltage data of the electric appliance, has low requirements on hardware, only needs to collect the data of a single device in the early stage, sample data does not need to combine the data of the electric appliance, reduces the data collection amount, has simple algorithm, can be conveniently integrated into the hardware device, and is easy to popularize.
Drawings
FIG. 1 is a process flow of an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and the following embodiments.
As shown in fig. 1, the non-intrusive appliance quantity identification method includes the following steps:
s1, when N electric appliances run independently, obtaining the individual real-time current of the preset sampling number of each electric appliance with the same phase as a starting point, wherein the preset sampling number is more than or equal to the current period divided by the sampling period, N is more than or equal to 2, and the individual real-time current of the kth sampling relative to the starting point of the kth electric appliance is recorded as ikt，k∈[1,N]Let the predetermined number of samples be B, t ∈ [1, B ]]；
S2, when N electric appliances are actually operated and the number of the operated electric appliances is unknown, acquiring total real-time current of the N electric appliances with the preset sampling number by taking the same phase as a starting point, and recording the total real-time current of the t-th sampling as it，t∈[1,B]；
S3, setting the value range of the operation quantity of each electric appliance in actual operation in the step S2, and generating an initial solution according to the value range to form an initial solution set, wherein the initial solution corresponds to the operation quantity predicted by each electric appliance in the step S2;
s4, according to the individual real-time current and the overall real-time current, judging whether the initial solution in the initial solution set meets a preset effective condition or not, if so, storing the corresponding initial solution as an effective solution in an effective solution set; if none of the initial solutions satisfies the predetermined validity condition, go to step S2;
s5, calculating the corresponding expected total real-time current according to the individual real-time current and the effective solutions, calculating the matching degree of the expected total real-time current corresponding to each effective solution and the total real-time current in the step S2, and selecting the effective solution with the highest matching degree as the optimal solution of the initial solution set in the step S2.
It should be noted that the collected currents are all currents when the electric appliances work in a steady state, the types of the N electric appliances are not a big type, it can be understood that the electric appliances represent one electric appliance as long as the electric appliance models are different, the individual real-time current is the current of each electric appliance when the electric appliance operates independently, the total real-time current is the total required current when the actual operation of N electric appliances is collected and the number of the operation of each electric appliance is unknown, the real-time current can be used as sample data, the total real-time current is used as measured data, the acquisition quantity of the individual real-time current of each electric appliance is equal to the acquisition quantity of the total real-time current, the initial phases of the acquired individual real-time current and the total real-time current are the same, the real-time current can be used as sample data, and the total real-time current can be used as actual measurement data, so that the comparison and judgment of the corresponding current values of the same acquisition point can be conveniently carried out subsequently. For step S4, the initial solutions may be sequentially determined, if a certain initial solution satisfies a predetermined valid condition, the certain initial solution is stored as a valid solution in the valid solution set, otherwise, the next initial solution is determined, and after the traversal is completed, if none of the initial solutions still satisfies the predetermined valid condition, step S2 is performed to obtain the current total real-time current again.
Preferably, the step S1 may include acquiring a real-time voltage, performing phase alignment to obtain a phase alignment point of the real-time voltage, and intercepting B real-time currents after the acquisition times corresponding to the phase alignment point as the individual real-time currents of the step S1, where:
s101, selecting N electric appliances as research objects, respectively collecting real-time current and real-time voltage of each electric appliance A times, and recording the t' th sampled real-time voltage of the kth electric appliance as vkt′Recording the real-time current of the t 'sampling of the kth electrical appliance as i'kt′，k∈[1,N]，t′∈[1,A]A is more than or equal to B; taking the average value of the maximum value and the minimum value of the real-time voltage of the kth electric appliance as the voltage v corresponding to the initial 0 phase of the kth electric appliancepSetting the sampling frequency p corresponding to the initial 0-phase real-time voltage to be 0 and setting the current ergodic sampling frequency cThe initial value is 1;
s102, judging whether A is larger than or equal to c, if so, entering the step S103; otherwise, go to step S104;
s103, judging whether c is more than or equal to p and | vp-vkc| is less than or equal to a predetermined threshold value, vkcIf so, entering step S104, otherwise, increasing c by 1, and entering step S102;
s104, judging whether the real-time voltage after the current traversal sampling times is complete, if so, entering a step S106, otherwise, entering a step S105;
s105, increasing a preset amplitude value by a preset threshold value, setting p to be 0, and entering a step S102;
s106, judgment vkcWhether the real-time voltages of the next preset number meet the ascending trend or not is judged, if yes, p is set to be equal to c, and B real-time currents i 'are intercepted by taking the sampling times p as a starting point'kp～i′k(B+p-1)As individual real-time current of the corresponding appliance, i.e. setting ik1＝i′kp，ikB＝i′k(B+p-1)And the individual real-time current i of the kth type of electric appliance is obtained by analogyk1～ikB(ii) a Otherwise, the step S107 is carried out;
s107, increasing the predetermined threshold value by a predetermined amplitude value, setting p equal to c, increasing c by 1, and entering step S102.
And judging whether the real-time voltage is complete or not, wherein if A-c is more than or equal to B-1, the real-time voltage is complete, and if not, the real-time voltage is incomplete.
Similar to the phase alignment method, when the N electrical appliances are actually operated and the actual number of each electrical appliance is unknown, the phase alignment point of the real-time voltage may be obtained by performing phase alignment using the collected corresponding real-time voltage, and B real-time currents after the collection times corresponding to the phase alignment point are intercepted as the total real-time current in step S2, where the step S2 may include:
s201, when N electrical appliances are actually operated and the actual quantity of each electrical appliance is unknown, acquiring real-time current and real-time voltage in A actual operation, and recording the t' th sampled real-time voltage as vt', note the real-time current of the t' th sampling as i′t，t′∈[1,A]A is more than or equal to B; the average value of the maximum value and the minimum value of the real-time voltage is used as the voltage v 'corresponding to the initial 0 phase'pSetting the sampling frequency p corresponding to the initial 0-phase real-time voltage value as 0, and setting the initial value of the current traversed sampling frequency c as 1;
s202, judging whether A is larger than or equal to c, if so, entering the step S203; otherwise, go to step S204;
s203, judging whether c is more than or equal to p and | v'p-vc| is less than or equal to a predetermined threshold value, vcIf the real-time voltage sampled for the c-th time is the real-time voltage sampled for the c-th time, the step S204 is performed, otherwise, the step C is increased by 1, and the step S202 is performed;
s204, judging whether the real-time voltage after the current traversal sampling times is complete, if so, entering a step S206, otherwise, entering a step S205;
s205, increasing a predetermined amplitude value by a predetermined threshold value, setting p to be 0, and entering step S202;
s206, judgment vcWhether the real-time voltages of the next preset number meet the ascending trend or not is judged, if yes, p is set to be equal to c, and B real-time currents i 'are intercepted by taking the sampling times p as a starting point'p～i′B+p-1As a total real-time current, i.e. setting i1＝i′p，iB＝i′B+p-1And so on to obtain the real-time current i1～iB(ii) a Otherwise, go to step S207;
s207, increasing the predetermined threshold value by a predetermined amplitude value, setting p equal to c, increasing c by 1, and entering step S202.
Similarly, whether the real-time voltage is complete or not can be judged by judging whether A-c is more than or equal to B-1, the real-time voltage is complete, and otherwise, the real-time voltage is incomplete.
In view of the efficiency of the optimal solution calculation, preferably, the step S3 may include:
s301, setting the value range of the running quantity of each electric appliance in the step S2;
and S302, randomly generating Q initial solutions according to the value range to form an initial solution set.
The value range may include a maximum value of the number of operations of each appliance.
In consideration of the diversity of the data to be compared subsequently, the step S3 may include:
calculating the maximum value and the minimum value of the individual real-time current of each electrical appliance, calculating the difference value of the maximum value and the minimum value of the individual real-time current of each electrical appliance as an individual amplitude difference value, and recording the maximum value, the minimum value and the individual amplitude difference value of the individual real-time current of the kth electrical appliance as
And Dk；
Calculating the total real-time current i1～iBThe effective value, the maximum value and the minimum value of (A) are sequentially recorded as
iUAnd iLAnd calculating the difference value between the maximum value and the minimum value of the total real-time current as a total amplitude difference value D.
In order to ensure the validity of the initial solution, the predetermined validity condition may include:
recording the maximum value and the minimum value of the maximum values and the minimum values of the individual real-time currents corresponding to all the non-zero operation quantities in the initial solution as iU1And iL1Maximum value of total real-time current iUI is greater than or equal to a predetermined multipleU1And the minimum value i of the total real-time currentLIs less than or equal to iL1The preset multiple is at least the operation quantity of the electric appliance corresponding to the maximum value of the real-time current when each electric appliance operates individually in the initial solution;
and/or, in the effective solution, the sum of the products of the running quantity of each electric appliance and the individual amplitude difference value of the corresponding electric appliance minus the total amplitude difference value is less than or equal to a preset difference value, and the initial solution is recorded as { F1w～FNw}，w∈[1,Q]Q is the number of initial solutions, FkwRepresenting the predicted operation number of the kth electric appliance by the w initial solution; for the w-th valid solution,
less than or equal to a predetermined difference;
and/or recording the maximum value and the minimum value of the effective values of the individual real-time currents of the kth electric appliance obtained for multiple times as
And
the effective value of the total real-time current is more than or equal to the sum of products of the quantity of each electric appliance in the effective solution and the minimum value of the effective value of the corresponding individual real-time current and less than or equal to the sum of products of the quantity of each electric appliance in the effective solution and the maximum value of the effective value of the corresponding individual real-time current, namely the sum
The judgment of the effectiveness of the initial solution in the initial solution space is respectively and separately carried out, and traversal can be carried out in sequence; if the three conditions are judged simultaneously, the filtering effect of the initial solution is better.
Considering the overall difference between the expected overall real-time current corresponding to the initial solution and the overall real-time current in step S2, the difference value of each point may be considered as the overall difference, and preferably, the step S5 may include:
s501, recording the effective value of the individual real-time current of the kth electric appliance as
Noting that the number of valid solutions is R, the corresponding y-th valid solution is { F'1y～F′Ny}，y∈[1,R]，F′kyCalculating the current ratio of each electric appliance corresponding to the effective solution for the operation number of the kth electric appliance in the yth effective solution, and recording the current ratio corresponding to the yth effective solution as Gky，
S502, taking the current ratio of each electric appliance as the rightMultiplying the weighted individual real-time current by the corresponding individual real-time current to obtain the weighted individual real-time current, effectively solving the corresponding expected overall real-time current as the sum of the weighted individual real-time currents of all the electric appliances at the corresponding acquisition points, and recording the expected overall real-time current sampled for the t time under the y-th effective solution as it′y，
S503, calculating the variance between the expected real-time current and the total real-time current in the step S2, and recording the variance corresponding to the y-th effective solution as Xy，
The variance corresponding to all valid solutions is noted as X1～XR；
S504, taking the variance as the matching degree of the corresponding effective solution, and selecting X1～XRThe effective solution corresponding to the maximum value in the initial solution set is used as the optimal solution of the initial solution set.
On the basis of the solution of the matching degree, the effective solution of the influence of the amplitude difference between the expected total real-time current and the total real-time current in step S2 and the influence of the amplitude difference between the expected total real-time current and the amplitude difference between the total real-time current in step S2 on the matching degree is added, so as to improve the accuracy of the matching degree judgment, and the step S5 may include:
s501, recording the effective value of the individual real-time current of the kth electric appliance as
Noting that the number of valid solutions is R, the corresponding y-th valid solution is { F'1y～F′Ny}，y∈[1,R]，F′kyCalculating the current ratio of each electric appliance corresponding to the effective solution for the operation number of the kth electric appliance in the yth effective solution, and recording the current ratio corresponding to the yth effective solution as Gky，
S502, multiplying the current ratio of each electric appliance by the corresponding individual real-time current to obtain the weighted individual real-time current, wherein the expected overall real-time current corresponding to the effective solution is the sum of the weighted individual real-time currents of all the electric appliances at the corresponding acquisition points, and the expected overall real-time current sampled at the t time under the y-th effective solution is recorded as i'ty，
S503, calculating the variance between the expected real-time current and the total real-time current in the step S2, and recording the variance corresponding to the y-th effective solution as Xy，
The variance corresponding to all valid solutions is noted as X1～XRTo X1～XRGiving corresponding 1 st preset weight to R th preset weight according to the sorting size to obtain new variance corresponding to all effective solutions, and marking as X1′～XR′；
S504, calculating the sum of the running quantity of each electric appliance in the effective solution multiplied by the individual amplitude difference value of each electric appliance to subtract the total amplitude difference value to obtain an amplitude difference value, and recording the amplitude difference value corresponding to the yth effective solution as Zy1，
The difference of the amplitude difference corresponding to all the effective solutions is recorded as Z11～ZR1(ii) a To Z11～ZR1Giving corresponding 1 ' preset weight to R ' preset weight according to the sorting size to obtain new amplitude difference values corresponding to all effective solutions, and recording the new amplitude difference values as Z '11～Z′R1；
S505, calculating the sum of the running quantity of each electric appliance in the effective solution multiplied by the effective value of the real-time current corresponding to each electric appliance individual and subtracting the effective value of the real-time current to obtain an effective value difference value, and recording the effective value difference value corresponding to the yth effective solution as Zy2，
The difference of the effective values corresponding to all effective solutions is recorded as Z12～ZR2(ii) a To Z12～ZR2Giving corresponding 1 st ' preset weight to the R th ' preset weight according to the sorting size to obtain new effective value difference values corresponding to all effective solutions, and recording the difference values as Z '12～Z′R2；
S506, corresponding to the variance X of the effective solution1′～XR', amplitude difference value Z'11～Z′R1And an effective difference value Z'12～Z′R2And adding the effective solutions to obtain the matching degree of the corresponding effective solutions, and selecting the effective solution with the highest matching degree as the optimal solution of the initial solution set.
In order to ensure the accuracy of the sample data, i.e., the real-time current of the individual, the step S1 may be executed multiple times to obtain multiple groups of individual real-time currents, and the effective value of the individual real-time current of the kth electrical appliance is an average value of the effective values of the individual real-time currents of the kth electrical appliance in the multiple groups of individual real-time currents.
As a preferable aspect of the above method, the 1 st to R-th predetermined weights may be sequentially set to W1、2W1……RW1The step of giving the corresponding 1 st to R-th predetermined weights according to the sorting size to obtain new variances corresponding to all valid solutions includes: the least ranked variance is given a weight of W1The largest ranked variance is given weight RW1And so on;
the above-mentioned 1 'th to R' th predetermined weights may be sequentially set to W2、2W2……RW2The step of giving the corresponding 1 st 'to R' predetermined weights according to the sorting order to obtain the new amplitude difference values corresponding to all valid solutions includes: the smallest ordered amplitude difference value is given a weight of W2The greatest ranked difference value is weighted by RW2And so on;
the above-mentioned 1 st 'to R' predetermined weights may be sequentially set to W3、2W3……RW3Above-mentioned pressThe step of giving the ordering size to the corresponding 1 st 'preset weight to the R' preset weight to obtain the new effective value difference corresponding to all the effective solutions comprises the following steps: the smallest sorted effective value difference is given weight W3The most significant difference value in the sequence is weighted by RW3And so on. RW (R-W)1Is R times W1By analogy, it should be noted that the weights are given, that is, the weights are multiplied by the corresponding weights.
Claims (10)
1. The non-invasive electric appliance quantity identification method is characterized by comprising the following steps:
s1, when N electric appliances run independently, obtaining the individual real-time current of the preset sampling number of each electric appliance with the same phase as a starting point, wherein the preset sampling number is more than or equal to the current period divided by the sampling period, N is more than or equal to 2, and the individual real-time current of the kth sampling of the kth electric appliance relative to the starting point is recorded as ikt，k∈[1,N]Let the predetermined number of samples be B, t ∈ [1, B ]]；
S2, when N electric appliances are actually operated and the number of the operated electric appliances is unknown, acquiring total real-time current of the N electric appliances with the preset sampling number by taking the same phase as a starting point, and recording the total real-time current of the t-th sampling as it，t∈[1,B]；
S3, setting the value range of the operation quantity of each electric appliance in actual operation in the step S2, and generating an initial solution according to the value range to form an initial solution set, wherein the initial solution corresponds to the predicted operation quantity of each electric appliance in the step S2;
s4, according to the individual real-time current and the overall real-time current, judging whether the initial solution in the initial solution set meets a preset effective condition or not, if so, storing the corresponding initial solution as an effective solution in an effective solution set; if none of the initial solutions satisfies the predetermined validity condition, go to step S2;
s5, calculating expected total real-time currents corresponding to the individual real-time currents and the effective solutions, calculating the matching degrees of the expected total real-time currents corresponding to the effective solutions and the total real-time currents in the step S2, and selecting the effective solution with the highest matching degree as the optimal solution of the initial solution set in the step S2; the expected total real-time current corresponding to the effective solution is the sum of the weighted individual real-time currents of all the electric appliances at the corresponding acquisition points.
2. The non-invasive electrical quantity recognition method as set forth in claim 1, wherein said step S1 includes:
s101, selecting N electric appliances as research objects, respectively collecting real-time current and real-time voltage of each electric appliance A times, and recording the t' th sampled real-time voltage of the kth electric appliance as vkt′Recording the real-time current of the t 'sampling of the kth electrical appliance as i'kt′，k∈[1,N]，t′∈[1,A]A is more than or equal to B; taking the average value of the maximum value and the minimum value of the real-time voltage of the kth electric appliance as the voltage v corresponding to the initial 0 phase of the kth electric appliancepSetting the sampling frequency p corresponding to the initial 0-phase real-time voltage as 0 and setting the initial value of the current traversed sampling frequency c as 1;
s102, judging whether A is larger than or equal to c, if so, entering the step S103; otherwise, go to step S104;
s103, judging whether c is more than or equal to p and | vp-vkc| is less than or equal to a predetermined threshold value, vkcIf so, entering step S104, otherwise, increasing c by 1, and entering step S102;
s104, judging whether the real-time voltage after the current traversal sampling times is complete, if so, entering a step S106, otherwise, entering a step S105;
s105, increasing a preset amplitude value by a preset threshold value, setting p to be 0, and entering a step S102;
s106, judgment vkcWhether the real-time voltages of the next preset number meet the ascending trend or not is judged, if yes, p is set to be equal to c, and B real-time currents i 'are intercepted by taking the sampling times p as a starting point'kp～i′k(B+p-1)As individual real-time current of the corresponding appliance, i.e. setting ik1＝i′kp，ikB＝i′k(B+p-1)And the individual real-time current i of the kth type of electric appliance is obtained by analogyk1～ikB(ii) a Otherwise, the step S107 is carried out;
s107, increasing the predetermined threshold value by a predetermined amplitude value, setting p equal to c, increasing c by 1, and entering step S102.
3. The non-invasive electrical quantity recognition method as set forth in claim 1, wherein said step S2 includes:
s201, when N electrical appliances are actually operated and the actual quantity of each electrical appliance is unknown, acquiring real-time current and real-time voltage in A actual operation, and recording the t' th sampled real-time voltage as vt′And recording the real-time current of the t 'th sampling as i't′，t′∈[1,A]A is more than or equal to B; the average value of the maximum value and the minimum value of the real-time voltage is used as the voltage v 'corresponding to the initial 0 phase'pSetting the sampling frequency p corresponding to the initial 0-phase real-time voltage value as 0, and setting the initial value of the current traversed sampling frequency c as 1;
s202, judging whether A is larger than or equal to c, if so, entering the step S203; otherwise, go to step S204;
s203, judging whether c is more than or equal to p and | v'p-vc| is less than or equal to a predetermined threshold value, vcIf the real-time voltage sampled for the c-th time is the real-time voltage sampled for the c-th time, the step S204 is performed, otherwise, the step C is increased by 1, and the step S202 is performed;
s204, judging whether the real-time voltage after the current traversal sampling times is complete, if so, entering a step S206, otherwise, entering a step S205;
s205, increasing a predetermined amplitude value by a predetermined threshold value, setting p to be 0, and entering step S202;
s206, judgment vcWhether the real-time voltages of the next preset number meet the ascending trend or not is judged, if yes, p is set to be equal to c, and B real-time currents i 'are intercepted by taking the sampling times p as a starting point'p～i′B+p-1As a total real-time current, i.e. setting i1＝i′p，iB＝i′B+p-1And so on to obtain the real-time current i1～iB(ii) a Otherwise, go to step S207;
s207, increasing the predetermined threshold value by a predetermined amplitude value, setting p equal to c, increasing c by 1, and entering step S202.
4. The non-invasive electrical quantity recognition method as set forth in claim 1, wherein said step S3 includes:
s301, setting the value range of the running quantity of each electric appliance in the step S2;
and S302, randomly generating Q initial solutions according to the value range to form an initial solution set.
5. The non-invasive electrical quantity recognition method as claimed in claim 1, wherein said step S3 is followed by comprising:
calculating the maximum value and the minimum value of the individual real-time current of each electrical appliance, calculating the difference value of the maximum value and the minimum value of the individual real-time current of each electrical appliance as an individual amplitude difference value, and recording the maximum value, the minimum value and the individual amplitude difference value of the individual real-time current of the kth electrical appliance as
And Dk；
Calculating the total real-time current i1～iBThe effective value, the maximum value and the minimum value of (A) are sequentially recorded as
iUAnd iLAnd calculating the difference value between the maximum value and the minimum value of the total real-time current as a total amplitude difference value D.
6. The non-invasive electrical quantity recognition method as set forth in claim 5, wherein said step S4 includes:
the predetermined valid conditions include:
recording the maximum value and the minimum value of the maximum values and the minimum values of the individual real-time currents corresponding to all the non-zero operation quantities in the initial solution as iU1And iL1Maximum value of total real-time current iUI is greater than or equal to a predetermined multipleU1And the minimum value i of the total real-time currentLIs less than or equal to iL1The preset multiple is at least the operation quantity of the electric appliance corresponding to the maximum value of the real-time current of each electric appliance during the individual operation in the initial solution;
and/or, subtracting the total amplitude difference value from the sum of the products of the running quantity of each electric appliance and the individual amplitude difference value of the corresponding electric appliance in the effective solution, wherein the total amplitude difference value is less than or equal to a preset difference value;
and/or recording the maximum value and the minimum value of the effective values of the individual real-time currents of the kth electric appliance obtained for multiple times as
And
the effective value of the total real-time current is more than or equal to the sum of products of the quantity of each electric appliance in the effective solution and the minimum value of the effective value of the corresponding individual real-time current and less than or equal to the sum of products of the quantity of each electric appliance in the effective solution and the maximum value of the effective value of the corresponding individual real-time current.
7. The non-invasive electrical quantity recognition method as set forth in claim 5, wherein said step S5 includes:
s501, recording the effective value of the individual real-time current of the kth electric appliance as
Noting that the number of valid solutions is R, the corresponding y-th valid solution is { F'1y～F′Ny}，y∈[1,R]，F′kyCalculating the current ratio of each electric appliance corresponding to the effective solution for the operation number of the kth electric appliance in the yth effective solution, and recording the current ratio corresponding to the yth effective solution as Gky，
S502, multiplying the current ratio of each electric appliance by the corresponding individual real-time current to obtain the weighted individual real-time current, and effectively solving the corresponding expected total currentThe bulk real-time current is the sum of weighted individual real-time currents of all the electric appliances at corresponding acquisition points, and the expected total real-time current of the t sampling under the y effective solution is recorded as i'ty，
S503, calculating the variance between the expected real-time current and the total real-time current in the step S2, and recording the variance corresponding to the y-th effective solution as Xy，
The variance corresponding to all valid solutions is noted as X1～XR；
S504, taking the variance as the matching degree of the corresponding effective solution, and selecting X1～XRThe effective solution corresponding to the maximum value in the initial solution set is used as the optimal solution of the initial solution set.
8. The non-invasive electrical quantity recognition method as set forth in claim 5, wherein said step S5 includes:
s501, recording the effective value of the individual real-time current of the kth electric appliance as
Noting that the number of valid solutions is R, the corresponding y-th valid solution is { F'1y～F′Ny}，y∈[1,R]，F′kyCalculating the current ratio of each electric appliance corresponding to the effective solution for the operation number of the kth electric appliance in the yth effective solution, and recording the current ratio corresponding to the yth effective solution as Gky，
S502, multiplying the current ratio of each electric appliance by the corresponding individual real-time current to obtain the weighted individual real-time current, effectively solving the corresponding expected total real-time current as the sum of the weighted individual real-time currents of all the electric appliances at the corresponding acquisition points, and recording the sumThe expected total real-time current of the tth effective solution sample is i'ty，
S503, calculating the variance between the expected real-time current and the total real-time current in the step S2, and recording the variance corresponding to the y-th effective solution as Xy，
The variance corresponding to all valid solutions is noted as X1～XRTo X1～XRGiving corresponding 1 st preset weight to R th preset weight according to the sorting size to obtain new variance corresponding to all effective solutions, and marking as X1′～XR′；
S504, calculating the sum of the running quantity of each electric appliance in the effective solution multiplied by the individual amplitude difference value of each electric appliance and subtracting the total amplitude difference value to obtain an amplitude difference value, and recording the amplitude difference value corresponding to the yth effective solution as Zy1，
The difference of the amplitude difference corresponding to all the effective solutions is recorded as Z11～ZR1(ii) a To Z11～ZR1Giving corresponding 1 ' preset weight to R ' preset weight according to the sorting size to obtain new amplitude difference values corresponding to all effective solutions, and recording the new amplitude difference values as Z '11～Z′R1；
S505, calculating the sum of the running quantity of each electric appliance in the effective solution multiplied by the effective value of the real-time current corresponding to each electric appliance individual and subtracting the effective value of the real-time current to obtain an effective value difference value, and recording the effective value difference value corresponding to the yth effective solution as Zy2，
The difference of the effective values corresponding to all effective solutions is recorded as Z12～ZR2(ii) a To Z12～ZR2Assigned to corresponding according to the size of the sequenceObtaining effective value difference values recorded as Z 'corresponding to all the new effective solutions from the 1 st' predetermined weight to the R th 'predetermined weight'12～Z′R2；
S506, corresponding to the variance X of the effective solution1′～XR', amplitude difference value Z'11～Z′R1And an effective difference value Z'12～Z′R2And adding the effective solutions to obtain the matching degree of the corresponding effective solutions, and selecting the effective solution with the highest matching degree as the optimal solution of the initial solution set.
9. The non-invasive electrical apparatus quantity identification method according to claim 7 or 8, wherein the step S1 is executed for a plurality of times to obtain a plurality of groups of individual real-time currents, and the effective value of the individual real-time current of the kth electrical apparatus is an average value of the effective values of the individual real-time currents of the kth electrical apparatus in the plurality of groups of individual real-time currents.
10. The non-invasive electrical appliance quantity recognition method as claimed in claim 8, wherein the 1 st to R-th predetermined weights are sequentially set to W1、2W1……RW1The step of giving the corresponding 1 st to R-th predetermined weights according to the sorting size to obtain new variances corresponding to all valid solutions includes: the least ranked variance is given a weight of W1The largest ranked variance is given weight RW1And so on;
and/or, the 1 'th to R' th predetermined weights may be sequentially set to W2、2W2……RW2The step of giving the corresponding 1 st 'to R' predetermined weights according to the sorting size to obtain new amplitude difference values corresponding to all valid solutions includes: the smallest ordered amplitude difference value is given a weight of W2The greatest ranked difference value is weighted by RW2And so on;
and/or, the 1 st 'to R' predetermined weights may be sequentially set to W3、2W3……RW3The 1 st 'predetermined weight is assigned to the corresponding 1 st' according to the sorting sizeThe obtaining of the new valid value difference values corresponding to all valid solutions by the predetermined weight of R ″ includes: the smallest sorted effective value difference is given weight W3The most significant difference value in the sequence is weighted by RW3And so on.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536276.6A CN109613362B (en) | 2018-12-14 | 2018-12-14 | Non-invasive electric appliance quantity identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811536276.6A CN109613362B (en) | 2018-12-14 | 2018-12-14 | Non-invasive electric appliance quantity identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109613362A CN109613362A (en) | 2019-04-12 |
| CN109613362B true CN109613362B (en) | 2021-02-26 |
Family
ID=66010116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811536276.6A Active CN109613362B (en) | 2018-12-14 | 2018-12-14 | Non-invasive electric appliance quantity identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109613362B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110146758B (en) * | 2019-05-28 | 2021-02-09 | 四川长虹电器股份有限公司 | Non-invasive electrical appliance identification method based on cross entropy |
| CN110244149B (en) * | 2019-07-05 | 2021-03-16 | 四川长虹电器股份有限公司 | Non-invasive electrical appliance identification method based on current amplitude standard deviation |
| CN110244150B (en) * | 2019-07-05 | 2021-03-16 | 四川长虹电器股份有限公司 | Non-invasive electrical appliance identification method based on root mean square and standard deviation |
| CN110850220A (en) * | 2019-11-29 | 2020-02-28 | 苏州大学 | Electrical appliance detection method, device and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001230A (en) * | 2012-11-16 | 2013-03-27 | 天津大学 | Non-invasive power load monitoring and decomposing current mode matching method |
| CN105866581A (en) * | 2016-04-08 | 2016-08-17 | 湖南工业大学 | Electric appliance type identification method |
| CN106022645A (en) * | 2016-06-07 | 2016-10-12 | 李祖毅 | Non-intruding type on-line and real-time electric power load identification method and identification system |
| CN106646026A (en) * | 2016-11-11 | 2017-05-10 | 华北电力大学 | Non-intrusive household appliance load identification method |
| CN106872824A (en) * | 2017-02-15 | 2017-06-20 | 宁波华创锐科智能科技有限公司 | A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics |
| CN107516115A (en) * | 2017-09-06 | 2017-12-26 | 中国南方电网有限责任公司 | A kind of load model canonical parameter extracting method based on k central point algorithms |
| CN108879702A (en) * | 2018-06-21 | 2018-11-23 | 浙江大学 | A kind of power consumption control system based on household load decomposition |
-
2018
- 2018-12-14 CN CN201811536276.6A patent/CN109613362B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103001230A (en) * | 2012-11-16 | 2013-03-27 | 天津大学 | Non-invasive power load monitoring and decomposing current mode matching method |
| CN105866581A (en) * | 2016-04-08 | 2016-08-17 | 湖南工业大学 | Electric appliance type identification method |
| CN106022645A (en) * | 2016-06-07 | 2016-10-12 | 李祖毅 | Non-intruding type on-line and real-time electric power load identification method and identification system |
| CN106646026A (en) * | 2016-11-11 | 2017-05-10 | 华北电力大学 | Non-intrusive household appliance load identification method |
| CN106872824A (en) * | 2017-02-15 | 2017-06-20 | 宁波华创锐科智能科技有限公司 | A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics |
| CN107516115A (en) * | 2017-09-06 | 2017-12-26 | 中国南方电网有限责任公司 | A kind of load model canonical parameter extracting method based on k central point algorithms |
| CN108879702A (en) * | 2018-06-21 | 2018-11-23 | 浙江大学 | A kind of power consumption control system based on household load decomposition |
Non-Patent Citations (1)
| Title |
|---|
| 基于稳态特征的非侵入式负荷辨识系统的设计与实现;张志豪;《中国优秀硕士学位论文全文数据库》;20180915(第9期);C042-183 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109613362A (en) | 2019-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109613362B (en) | Non-invasive electric appliance quantity identification method | |
| CN108429254B (en) | non-invasive electric load identification method | |
| Munshi et al. | Unsupervised nonintrusive extraction of electrical vehicle charging load patterns | |
| CN108899892A (en) | One kind being based on CNN non-intrusion type power load decomposition method | |
| Ghosh et al. | Artificial bee colony optimization based non-intrusive appliances load monitoring technique in a smart home | |
| CN109975673B (en) | Method for identifying fault arc at direct current side of photovoltaic microgrid | |
| CN106872824A (en) | A kind of network load appliance type identification and the method and its device of different electrical equipment electricity statistics | |
| WO2019128844A1 (en) | Non-invasive identification method of microwave oven operation based on hybrid criteria | |
| CN109633301B (en) | Non-invasive electrical appliance load identification method based on quantum genetic optimization | |
| CN106093565A (en) | A kind of electricity subentry measurement method and device based on steady state characteristic Waveform Matching | |
| CN111639586B (en) | Non-invasive load identification model construction method, load identification method and system | |
| CN111722028A (en) | Load identification method based on high-frequency data | |
| Sun et al. | Non-intrusive load monitoring system framework and load disaggregation algorithms: a survey | |
| CN106464988A (en) | Energy management system | |
| CN106680621B (en) | A kind of resident load electricity consumption recognition methods based on current signal separation | |
| CN106777005A (en) | User power utilization behavior analysis method based on big data technological improvement clustering algorithm | |
| CN108595376B (en) | Non-invasive load identification method for distinguishing fixed-frequency air conditioner and percussion drill | |
| CN110555787B (en) | Non-invasive load identification method based on improved particle swarm optimization | |
| CN112633924A (en) | Cell electric energy substitution demand analysis method based on load decomposition | |
| CN105305437B (en) | The triple confidence level matching discrimination methods of electric load | |
| CN110146758B (en) | Non-invasive electrical appliance identification method based on cross entropy | |
| CN115563583A (en) | Non-invasive load monitoring method based on multi-physical quantity fusion | |
| CN114355275A (en) | Electric energy meter load monitoring method, system and device and computer readable storage medium | |
| CN114943367A (en) | Non-invasive load identification method based on BP neural network model | |
| CN110244149B (en) | Non-invasive electrical appliance identification method based on current amplitude standard deviation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |